Teachers, Learners and Oracles
Achilles A. Beros, Colin de la Higuera

TL;DR
This paper compares the efficiency of learning computably enumerable sets with teachers versus membership oracles, revealing significant resource differences under polynomial and exponential bounds.
Contribution
It introduces a family of sets that are learnable with teachers in polynomial time but require exponential resources with membership oracles, highlighting fundamental distinctions in learning models.
Findings
Sets learnable with teachers in polynomial time
Sets requiring exponential resources with membership oracles
Comparison across four measures of efficient learning
Abstract
We exhibit a family of computably enumerable sets which can be learned within polynomial resource bounds given access only to a teacher, but which requires exponential resources to be learned given access only to a membership oracle. In general, we compare the families that can be learned with and without teachers and oracles for four measures of efficient learning.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
